Tag
KBMR is an MLLM-based retriever for knowledge-based visual question answering that uses semantic alignment to improve retrieval and VQA accuracy, showing significant gains over CLIP baselines.
IRIS is a training-free framework that uses frozen large language models to construct reusable identity representations for entities in knowledge graphs, enabling efficient entity alignment across different KGs without pair-dependent processing.
Proposes an entity alignment method for science and technology patents using graph convolution networks and BERT to fuse structural and attribute information, achieving better performance on benchmark datasets.